Learning endometriosis phenotypes from patient-generated data

Abstract Endometriosis is a systemic and chronic condition in women of childbearing age, yet a highly enigmatic disease with unresolved questions: there are no known biomarkers, nor established clinical stages. We here investigate the use of patient-generated health data and data-driven phenotyping...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Iñigo Urteaga, Mollie McKillop, Noémie Elhadad
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/e95ea8d5ac0a40e7ae6663bd16165d4b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e95ea8d5ac0a40e7ae6663bd16165d4b
record_format	dspace
spelling	oai:doaj.org-article:e95ea8d5ac0a40e7ae6663bd16165d4b2021-12-02T18:02:55ZLearning endometriosis phenotypes from patient-generated data10.1038/s41746-020-0292-92398-6352https://doaj.org/article/e95ea8d5ac0a40e7ae6663bd16165d4b2020-06-01T00:00:00Zhttps://doi.org/10.1038/s41746-020-0292-9https://doaj.org/toc/2398-6352Abstract Endometriosis is a systemic and chronic condition in women of childbearing age, yet a highly enigmatic disease with unresolved questions: there are no known biomarkers, nor established clinical stages. We here investigate the use of patient-generated health data and data-driven phenotyping to characterize endometriosis patient subtypes, based on their reported signs and symptoms. We aim at unsupervised learning of endometriosis phenotypes using self-tracking data from personal smartphones. We leverage data from an observational research study of over 4000 women with endometriosis that track their condition over more than 2 years. We extend a classical mixed-membership model to accommodate the idiosyncrasies of the data at hand, i.e., the multimodality and uncertainty of the self-tracked variables. The proposed method, by jointly modeling a wide range of observations (i.e., participant symptoms, quality of life, treatments), identifies clinically relevant endometriosis subtypes. Experiments show that our method is robust to different hyperparameter choices and the biases of self-tracking data (e.g., the wide variations in tracking frequency among participants). With this work, we show the promise of unsupervised learning of endometriosis subtypes from self-tracked data, as learned phenotypes align well with what is already known about the disease, but also suggest new clinically actionable findings. More generally, we argue that a continued research effort on unsupervised phenotyping methods with patient-generated health data via new mobile and digital technologies will have significant impact on the study of enigmatic diseases in particular, and health in general.Iñigo UrteagaMollie McKillopNoémie ElhadadNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 3, Iss 1, Pp 1-14 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Iñigo Urteaga Mollie McKillop Noémie Elhadad Learning endometriosis phenotypes from patient-generated data
description	Abstract Endometriosis is a systemic and chronic condition in women of childbearing age, yet a highly enigmatic disease with unresolved questions: there are no known biomarkers, nor established clinical stages. We here investigate the use of patient-generated health data and data-driven phenotyping to characterize endometriosis patient subtypes, based on their reported signs and symptoms. We aim at unsupervised learning of endometriosis phenotypes using self-tracking data from personal smartphones. We leverage data from an observational research study of over 4000 women with endometriosis that track their condition over more than 2 years. We extend a classical mixed-membership model to accommodate the idiosyncrasies of the data at hand, i.e., the multimodality and uncertainty of the self-tracked variables. The proposed method, by jointly modeling a wide range of observations (i.e., participant symptoms, quality of life, treatments), identifies clinically relevant endometriosis subtypes. Experiments show that our method is robust to different hyperparameter choices and the biases of self-tracking data (e.g., the wide variations in tracking frequency among participants). With this work, we show the promise of unsupervised learning of endometriosis subtypes from self-tracked data, as learned phenotypes align well with what is already known about the disease, but also suggest new clinically actionable findings. More generally, we argue that a continued research effort on unsupervised phenotyping methods with patient-generated health data via new mobile and digital technologies will have significant impact on the study of enigmatic diseases in particular, and health in general.
format	article
author	Iñigo Urteaga Mollie McKillop Noémie Elhadad
author_facet	Iñigo Urteaga Mollie McKillop Noémie Elhadad
author_sort	Iñigo Urteaga
title	Learning endometriosis phenotypes from patient-generated data
title_short	Learning endometriosis phenotypes from patient-generated data
title_full	Learning endometriosis phenotypes from patient-generated data
title_fullStr	Learning endometriosis phenotypes from patient-generated data
title_full_unstemmed	Learning endometriosis phenotypes from patient-generated data
title_sort	learning endometriosis phenotypes from patient-generated data
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/e95ea8d5ac0a40e7ae6663bd16165d4b
work_keys_str_mv	AT inigourteaga learningendometriosisphenotypesfrompatientgenerateddata AT molliemckillop learningendometriosisphenotypesfrompatientgenerateddata AT noemieelhadad learningendometriosisphenotypesfrompatientgenerateddata
_version_	1718378841946193920

Learning endometriosis phenotypes from patient-generated data

Ejemplares similares